Interaction-based group identity detection via reinforcement learning and artificial evolution

Corrado Grappiolo, Julian Togelius, Georgios N. Yannakakis

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We present a computational framework capable of inferring the existence of group identities, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial So- cieties (CAAS) by solely observing the flow of interactions occurring among the agents. Our modelling framework in- fers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups and assign group identities to the agents. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum (or Bargain) Social Dilemma Game, show that a cooperation learning phase, based on Reinforcement Learning, can pro- vide highly promising results for minimising the mismatch between the existing and the inferred group identities. The proposed method appears to be robust independently of the size and the ongoing social dynamics of the societies.

    Original languageEnglish (US)
    Title of host publicationGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion
    Pages1423-1430
    Number of pages8
    DOIs
    StatePublished - 2013
    Event15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013 - Amsterdam, Netherlands
    Duration: Jul 6 2013Jul 10 2013

    Other

    Other15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013
    CountryNetherlands
    CityAmsterdam
    Period7/6/137/10/13

    Fingerprint

    Reinforcement learning
    Reinforcement Learning
    Interaction
    Social Dilemma
    Social Dynamics
    Evolutionary Computation
    Experimental Investigation
    Evolutionary algorithms
    Social Networks
    Assign
    Partition
    Game
    Modeling
    Framework

    Keywords

    • Adaptive artificial societies
    • Evolutionary com- putation
    • Group identity detection
    • Reinforcement learning
    • Ul- timatum game

    ASJC Scopus subject areas

    • Computational Mathematics

    Cite this

    Grappiolo, C., Togelius, J., & Yannakakis, G. N. (2013). Interaction-based group identity detection via reinforcement learning and artificial evolution. In GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion (pp. 1423-1430) https://doi.org/10.1145/2464576.2482722

    Interaction-based group identity detection via reinforcement learning and artificial evolution. / Grappiolo, Corrado; Togelius, Julian; Yannakakis, Georgios N.

    GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. 2013. p. 1423-1430.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Grappiolo, C, Togelius, J & Yannakakis, GN 2013, Interaction-based group identity detection via reinforcement learning and artificial evolution. in GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. pp. 1423-1430, 15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013, Amsterdam, Netherlands, 7/6/13. https://doi.org/10.1145/2464576.2482722
    Grappiolo C, Togelius J, Yannakakis GN. Interaction-based group identity detection via reinforcement learning and artificial evolution. In GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. 2013. p. 1423-1430 https://doi.org/10.1145/2464576.2482722
    Grappiolo, Corrado ; Togelius, Julian ; Yannakakis, Georgios N. / Interaction-based group identity detection via reinforcement learning and artificial evolution. GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. 2013. pp. 1423-1430
    @inproceedings{3c7cafc6dbcc4e898c66ee200ccc0ffc,
    title = "Interaction-based group identity detection via reinforcement learning and artificial evolution",
    abstract = "We present a computational framework capable of inferring the existence of group identities, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial So- cieties (CAAS) by solely observing the flow of interactions occurring among the agents. Our modelling framework in- fers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups and assign group identities to the agents. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum (or Bargain) Social Dilemma Game, show that a cooperation learning phase, based on Reinforcement Learning, can pro- vide highly promising results for minimising the mismatch between the existing and the inferred group identities. The proposed method appears to be robust independently of the size and the ongoing social dynamics of the societies.",
    keywords = "Adaptive artificial societies, Evolutionary com- putation, Group identity detection, Reinforcement learning, Ul- timatum game",
    author = "Corrado Grappiolo and Julian Togelius and Yannakakis, {Georgios N.}",
    year = "2013",
    doi = "10.1145/2464576.2482722",
    language = "English (US)",
    isbn = "9781450319645",
    pages = "1423--1430",
    booktitle = "GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion",

    }

    TY - GEN

    T1 - Interaction-based group identity detection via reinforcement learning and artificial evolution

    AU - Grappiolo, Corrado

    AU - Togelius, Julian

    AU - Yannakakis, Georgios N.

    PY - 2013

    Y1 - 2013

    N2 - We present a computational framework capable of inferring the existence of group identities, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial So- cieties (CAAS) by solely observing the flow of interactions occurring among the agents. Our modelling framework in- fers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups and assign group identities to the agents. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum (or Bargain) Social Dilemma Game, show that a cooperation learning phase, based on Reinforcement Learning, can pro- vide highly promising results for minimising the mismatch between the existing and the inferred group identities. The proposed method appears to be robust independently of the size and the ongoing social dynamics of the societies.

    AB - We present a computational framework capable of inferring the existence of group identities, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial So- cieties (CAAS) by solely observing the flow of interactions occurring among the agents. Our modelling framework in- fers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups and assign group identities to the agents. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum (or Bargain) Social Dilemma Game, show that a cooperation learning phase, based on Reinforcement Learning, can pro- vide highly promising results for minimising the mismatch between the existing and the inferred group identities. The proposed method appears to be robust independently of the size and the ongoing social dynamics of the societies.

    KW - Adaptive artificial societies

    KW - Evolutionary com- putation

    KW - Group identity detection

    KW - Reinforcement learning

    KW - Ul- timatum game

    UR - http://www.scopus.com/inward/record.url?scp=84882423713&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84882423713&partnerID=8YFLogxK

    U2 - 10.1145/2464576.2482722

    DO - 10.1145/2464576.2482722

    M3 - Conference contribution

    AN - SCOPUS:84882423713

    SN - 9781450319645

    SP - 1423

    EP - 1430

    BT - GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion

    ER -